Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8297e91149c4c185b4b0a3f857f7638fa4977cef3cf8932fc03f325d581aa4
+oid sha256:ac165e2897d2100a29ac3e6f5f309cfef42a1c81abb40805351d78508b78cf41
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8363c525774792e31896aa48db7ff5117326a83fdee59c89b3bdf6cfc630d50
+oid sha256:c0fbf8c5588762abe802dd05aca42e893f55c85d67b7b62e9f249460e7bf8480
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c5db8e94417abcbd58becfbbb12ba218d246aa13fee8a678361827f866872d
+oid sha256:efb9acc3b2397977d3e61a7fafcf17439b2fd71d9da0428fa38cc7280a798198
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014660276289822385,
+  "epoch": 0.0187952260125928,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.1878,
       "step": 35
+    },
+    {
+      "epoch": 0.015036180810074242,
+      "grad_norm": 1.2875986099243164,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2164,
+      "step": 40
+    },
+    {
+      "epoch": 0.015036180810074242,
+      "eval_loss": 0.13373848795890808,
+      "eval_runtime": 36.5736,
+      "eval_samples_per_second": 30.651,
+      "eval_steps_per_second": 15.339,
+      "step": 40
+    },
+    {
+      "epoch": 0.01691570341133352,
+      "grad_norm": 0.1800977885723114,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1561,
+      "step": 45
+    },
+    {
+      "epoch": 0.0187952260125928,
+      "grad_norm": 0.278409481048584,
+      "learning_rate": 0.0,
+      "loss": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.0187952260125928,
+      "eval_loss": 0.13275748491287231,
+      "eval_runtime": 36.656,
+      "eval_samples_per_second": 30.582,
+      "eval_steps_per_second": 15.304,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1918439836876800.0,
+  "total_flos": 2468392590114816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null